vspec

vspec is a skill for Claude Code, Codex from disler/pi-agent-observability. It costs 85 tokens per session (3,136 once invoked), scanned A, original, MIT.

A workflow that turns a software requirement into a written implementation plan with matching architecture and data-flow diagrams. The plan and images are saved in the specs/ folder.

In plain words
What is it for?
Creating illustrated engineering specifications, including system architecture, communication flows, data models, and lifecycles, with one overview image and one diagram for each main section.
Why use it?
It helps developers understand how the parts of a proposed system fit together before implementation begins.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/disler/pi-agent-observability/vspec
Any agent
npx skills add disler/pi-agent-observability --skill vspec
Clone the repo
git clone --depth 1 https://github.com/disler/pi-agent-observability

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vspec

README.md
[![agentmods](https://agentmods.dev/badge/skills/disler/pi-agent-observability/vspec.svg)](https://agentmods.dev/skills/disler/pi-agent-observability/vspec)
Your own site
<a href="https://agentmods.dev/skills/disler/pi-agent-observability/vspec"><img src="https://agentmods.dev/badge/skills/disler/pi-agent-observability/vspec.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.03136
Opus 5 $0.00043 $0.01568
Sonnet 5 $0.00017 $0.00627
Haiku 4.5 $0.00009 $0.00314

Measured 5d ago against content hash 2421a2a912f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vspec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_image.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/vspec/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vspec

Purpose

Produce a written engineering implementation plan, then add a visual layer: a hero image plus one diagram per section. Each image is an information-rich, compressed, visual artifact — architecture, nodes, communication flow, data models, lifecycles — not a rendered wall of text. The images are thematically consistent across the whole spec and are linked back into the markdown so the plan reads like an illustrated blueprint.

Two phases, in order:

  1. Plan phase — build and save the raw markdown plan.
  2. Image phase — after the plan exists, generate and embed one image per section.

The image phase always runs after the raw plan is written.

Variables

USER_PROMPT: $1 ALL_ARGUMENTS: $ARGUMENTS PLAN_OUTPUT_DIRECTORY: specs/ IMAGE_GENERATOR: ~/.claude/skills/vspec/scripts/generate_image.py IMAGE_SIZE: 2048x1152 (wide 16:9 by default) IMAGE_QUALITY: high OUTPUT_IMAGE_FORMAT: png HERO_IMAGE_NAME: 00-hero.png MAX_TEXT_LABELS_PER_IMAGE: 10 IMAGE_MARKER_PREFIX: vspec

Instructions

Plan phase

  • IMPORTANT: If no USER_PROMPT is provided, stop and ask the user to provide it.
  • Carefully analyze the user's requirements provided in the USER_PROMPT variable.
  • Determine the task type (chore|feature|refactor|fix|enhancement) and complexity (simple|medium|complex).
  • Think deeply (ultrathink) about the best approach to implement the requested functionality or solve the problem.
  • Explore the codebase to understand existing patterns and architecture.
  • Follow the Plan Format below to create a comprehensive implementation plan.
  • Include all required sections and conditional sections based on task type and complexity.
  • Generate a descriptive, kebab-case filename based on the main topic of the plan.
  • Save the complete implementation plan to PLAN_OUTPUT_DIRECTORY/<descriptive-name>.md.
  • Ensure the plan is detailed enough that another developer could follow it to implement the solution.
  • Include code examples or pseudo-code where appropriate to clarify complex concepts.
  • Consider edge cases, error handling, and scalability concerns.

Read the full file on GitHub · 246 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 246 lines · 85 tokens per session scan A 2421a2a912f5

Subscribe to this mod's changes

vspec is a skill published in the GitHub repository disler/pi-agent-observability (143 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 3,136 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens